© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36139
    Prev
    Next
    INDEX
    Explanations

    Hirschsprung, honors, hi, space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inz
    0.68
    aan
    0.65
    सी
    0.63
    a
    0.62
    一定的
    0.61
    '
    0.61
    ा
    0.60
    多
    0.60
    ीन
    0.58
    oc
    0.57
    POSITIVE LOGITS
    р
    0.77
    ربي
    0.69
    ר
    0.66
    вов
    0.64
    cton
    0.64
    li
    0.63
    ди
    0.63
    ্স
    0.62
    м
    0.62
     indoct
    0.61
    Activations Density 0.003%

    No Known Activations